Local Contrast and Global Contextual Information Make Infrared Small Object Salient Again

Abstract

Infrared small object detection (ISOS) aims to segment small objects only covered with several pixels from clutter background in infrared images. It's of great challenge due to: 1) small objects lack of sufficient intensity, shape and texture information; 2) small objects are easily lost in the process where detection models, say deep neural networks, obtain high-level semantic features and image-level receptive fields through successive downsampling. This paper proposes a reliable detection model for ISOS, dubbed UCFNet, which can handle well the two issues. It builds upon central difference convolution (CDC) and fast Fourier convolution (FFC). On one hand, CDC can effectively guide the network to learn the contrast information between small objects and the background, as the contrast information is very essential in human visual system dealing with the ISOS task. On the other hand, FFC can gain image-level receptive fields and extract global information while preventing small objects from being overwhelmed. Experiments on several public datasets demonstrate that our method significantly outperforms the state-of-the-art ISOS models, and can provide useful guidelines for designing better ISOS deep models.

MI2T-UNet: Integrating Multi-Scale Input Image and Top-hat Context for Infrared Small Object Segmentation

“…Then, LAMA was proposed by Suvorov et al 39 to be effectively used for large mask inpainting. Wang et al 40 introduced a U-shape network with central difference convolution and fast Fourier convolution (UCFNet) to help the network capture different SIO sizes.…”